AI BENCHY Category
Coding Ranking
See which AI models perform best on Coding, which ones stay reliable, and where the biggest gaps appear. Sort by: Tests Correct ↑.
| Rank | Model | Company | Coding Score | Score | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|
| #124 | Qwen3.5-122B-A10B none | Qwen | 4.0 | 5.4 | 0/2 | 2.14s |
| #125 | GLM 5 Turbo none | Z.ai | 4.4 | 5.3 | 0/2 | 2.58s |
| #127 | Laguna Xs.2 none | Poolside | 2.5 | 5.3 | 0/1 | 1.96s |
| #129 | gpt-oss-120b none | OpenAI | 4.3 | 5.2 | 0/1 | 9.57s |
| #130 | Elephant Alpha none | Openrouter | 4.7 | 5.2 | 0/2 | 1.39s |
| #131 | DeepSeek V4 Flash none | DeepSeek | 4.8 | 5.1 | 0/2 | 24.5s |
| #132 | Qwen3 Coder Next none | Qwen | 5.4 | 5.1 | 0/2 | 2.01s |
| #134 | Nemotron 3 Super none | NVIDIA | 3.4 | 5.0 | 0/2 | 3.02s |
| #135 | Mistral Small 4 none | Mistral | 4.0 | 5.0 | 0/2 | 1.03s |
| #138 | GPT-4o-mini none | OpenAI | 3.2 | 4.9 | 0/2 | 2.05s |
| #140 | Trinity Large Preview none | Arcee AI | 4.9 | 4.8 | 0/1 | 14.3s |
| #141 | Qwen3 Coder Next medium | Qwen | 4.1 | 4.7 | 0/2 | 1.17s |
| #142 | Qwen3.5-9B none | Qwen | 4.4 | 4.6 | 0/2 | 5.39s |
| #143 | Mercury 2 none | Inception | 3.5 | 4.6 | 0/2 | 831ms |
| #144 | Hy3 preview none | Tencent | 2.3 | 4.6 | 0/1 | 4.56s |